Supervised and Unsupervised Learning of Parameterized Color Enhancement

TL;DR

This paper presents a novel approach to color enhancement using parameterized transformations learned through both supervised CNNs and unsupervised GANs, achieving state-of-the-art results on benchmark datasets and demonstrating strong generalization.

Contribution

It introduces a global parameterized color transformation framework for image enhancement, utilizing both supervised and unsupervised learning methods, including GANs with a circularity constraint.

Findings

Achieves state-of-the-art results on MIT-Adobe FiveK benchmark.

Demonstrates strong generalization to historical photos and dark video frames.

Validates effectiveness of parameterized transformations over traditional image-to-image models.

Abstract

We treat the problem of color enhancement as an image translation task, which we tackle using both supervised and unsupervised learning. Unlike traditional image to image generators, our translation is performed using a global parameterized color transformation instead of learning to directly map image information. In the supervised case, every training image is paired with a desired target image and a convolutional neural network (CNN) learns from the expert retouched images the parameters of the transformation. In the unpaired case, we employ two-way generative adversarial networks (GANs) to learn these parameters and apply a circularity constraint. We achieve state-of-the-art results compared to both supervised (paired data) and unsupervised (unpaired data) image enhancement methods on the MIT-Adobe FiveK benchmark. Moreover, we show the generalization capability of our method, by applying it on photos from the early 20th century and to dark video frames.